mirror of
https://github.com/johnkerl/miller.git
synced 2026-07-24 16:38:57 +00:00
826 lines
16 KiB
Text
826 lines
16 KiB
Text
'\" t
|
|
.\" Title: miller
|
|
.\" Author: [see the "AUTHOR" section]
|
|
.\" Generator: DocBook XSL Stylesheets v1.78.1 <http://docbook.sf.net/>
|
|
.\" Date: 09/14/2015
|
|
.\" Manual: \ \&
|
|
.\" Source: \ \&
|
|
.\" Language: English
|
|
.\"
|
|
.TH "MILLER" "1" "09/14/2015" "\ \&" "\ \&"
|
|
.\" -----------------------------------------------------------------
|
|
.\" * Define some portability stuff
|
|
.\" -----------------------------------------------------------------
|
|
.\" ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
|
.\" http://bugs.debian.org/507673
|
|
.\" http://lists.gnu.org/archive/html/groff/2009-02/msg00013.html
|
|
.\" ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
|
.ie \n(.g .ds Aq \(aq
|
|
.el .ds Aq '
|
|
.\" -----------------------------------------------------------------
|
|
.\" * set default formatting
|
|
.\" -----------------------------------------------------------------
|
|
.\" disable hyphenation
|
|
.nh
|
|
.\" disable justification (adjust text to left margin only)
|
|
.ad l
|
|
.\" -----------------------------------------------------------------
|
|
.\" * MAIN CONTENT STARTS HERE *
|
|
.\" -----------------------------------------------------------------
|
|
.SH "NAME"
|
|
miller \- sed, awk, cut, join, and sort for name\-indexed data such as CSV
|
|
.SH "SYNOPSIS"
|
|
.sp
|
|
.SH "DESCRIPTION"
|
|
.sp
|
|
With Miller you get to use named fields without needing to count positional indices\&. This is something the Unix toolkit always could have done, and arguably always should have done\&. It operates on key\-value\-pair data while the familiar Unix tools operate on integer\-indexed fields: if the natural data structure for the latter is the array, then Miller\(cqs natural data structure is the insertion\-ordered hash map\&. This encompasses a variety of data formats, including but not limited to the familiar CSV\&. (Miller can handle positionally\-indexed data as a special case\&.)
|
|
.SH "EXAMPLES"
|
|
.sp
|
|
.if n \{\
|
|
.RS 4
|
|
.\}
|
|
.nf
|
|
% mlr \-\-csv cut \-f hostname,uptime mydata\&.csv
|
|
% mlr \-\-csv sort \-f hostname,uptime mydata\&.csv
|
|
% mlr \-\-csv put \*(Aq$z = $x + 2\&.7*$y\*(Aq mydata\&.csv
|
|
% mlr \-\-csv filter \*(Aq$status != "down"\*(Aq mydata\&.csv
|
|
.fi
|
|
.if n \{\
|
|
.RE
|
|
.\}
|
|
.SH "OPTIONS"
|
|
.sp
|
|
In the following option flags, the version with "i" designates the input stream, "o" the output stream, and the version without prefix sets the option for both input and output stream\&. For example: \-\-irs sets the input record separator, \-\-ors the output record separator, and \-\-rs sets both the input and output separator to the given value\&.
|
|
.SS "SEPARATOR"
|
|
.PP
|
|
\-\-rs, \-\-irs, \-\-ors
|
|
.RS 4
|
|
Record separators, defaulting to newline
|
|
.RE
|
|
.PP
|
|
\-\-fs, \-\-ifs, \-\-ofs, \-\-repifs
|
|
.RS 4
|
|
Field separators, defaulting to ","
|
|
.RE
|
|
.PP
|
|
\-\-ps, \-\-ips, \-\-ops
|
|
.RS 4
|
|
Pair separators, defaulting to "="
|
|
.RE
|
|
.SS "DATA\-FORMAT"
|
|
.PP
|
|
\-\-dkvp, \-\-idkvp, \-\-odkvp
|
|
.RS 4
|
|
Delimited key\-value pairs, e\&.g "a=1,b=2" (default)
|
|
.RE
|
|
.PP
|
|
\-\-nidx, \-\-inidx, \-\-onidx
|
|
.RS 4
|
|
Implicitly\-integer\-indexed fields (Unix\-toolkit style)
|
|
.RE
|
|
.PP
|
|
\-\-csv, \-\-icsv, \-\-ocsv
|
|
.RS 4
|
|
Comma\-separated value (or tab\-separated with \-\-fs tab, etc\&.)
|
|
.RE
|
|
.PP
|
|
\-\-pprint, \-\-ipprint, \-\-opprint, \-\-right
|
|
.RS 4
|
|
Pretty\-printed tabular (produces no output until all input is in)
|
|
.RE
|
|
.PP
|
|
\-\-pprint, \-\-ipprint, \-\-opprint, \-\-right
|
|
.RS 4
|
|
Pretty\-printed tabular (produces no output until all input is in)
|
|
.RE
|
|
.sp
|
|
\-p is a keystroke\-saver for \-\-nidx \-\-fs space \-\-repifs
|
|
.SS "NUMERICAL FORMAT"
|
|
.PP
|
|
.RS 4
|
|
Sets the numerical format given a printf\-style format string\&.
|
|
.RE
|
|
.SS "OTHER"
|
|
.PP
|
|
.RS 4
|
|
Seeds the random number generator used for put/filter
|
|
urand()
|
|
with a number n of the form 12345678 or 0xcafefeed\&.
|
|
.RE
|
|
.SS "VERBS"
|
|
.sp
|
|
.it 1 an-trap
|
|
.nr an-no-space-flag 1
|
|
.nr an-break-flag 1
|
|
.br
|
|
.ps +1
|
|
\fBcat\fR
|
|
.RS 4
|
|
.sp
|
|
Usage: mlr cat
|
|
.sp
|
|
Passes input records directly to output\&. Most useful for format conversion\&.
|
|
.RE
|
|
.sp
|
|
.it 1 an-trap
|
|
.nr an-no-space-flag 1
|
|
.nr an-break-flag 1
|
|
.br
|
|
.ps +1
|
|
\fBcheck\fR
|
|
.RS 4
|
|
.sp
|
|
Usage: mlr check
|
|
.sp
|
|
Consumes records without printing any output\&. Useful for doing a well\-formatted check on input data\&.
|
|
.RE
|
|
.sp
|
|
.it 1 an-trap
|
|
.nr an-no-space-flag 1
|
|
.nr an-break-flag 1
|
|
.br
|
|
.ps +1
|
|
\fBcount-distinct\fR
|
|
.RS 4
|
|
.sp
|
|
Usage: mlr count\-distinct [options]
|
|
.sp
|
|
Prints number of records having distinct values for specified field names\&. Same as uniq \-c\&.
|
|
.PP
|
|
\-f {a,b,c}
|
|
.RS 4
|
|
Field names for distinct count\&.
|
|
.RE
|
|
.RE
|
|
.sp
|
|
.it 1 an-trap
|
|
.nr an-no-space-flag 1
|
|
.nr an-break-flag 1
|
|
.br
|
|
.ps +1
|
|
\fBcut\fR
|
|
.RS 4
|
|
.sp
|
|
Usage: mlr cut [options]
|
|
.sp
|
|
Passes through input records with specified fields included/excluded\&.
|
|
.PP
|
|
\-f {a,b,c}
|
|
.RS 4
|
|
Field names to include for cut\&.
|
|
.RE
|
|
.PP
|
|
\-o
|
|
.RS 4
|
|
Retain fields in the order specified here in the argument list\&. Default is to retain them in the order found in the input data\&.
|
|
.RE
|
|
.PP
|
|
\-x|\-\-complement
|
|
.RS 4
|
|
Exclude, rather that include, field names specified by \-f\&.
|
|
.RE
|
|
.RE
|
|
.sp
|
|
.it 1 an-trap
|
|
.nr an-no-space-flag 1
|
|
.nr an-break-flag 1
|
|
.br
|
|
.ps +1
|
|
\fBfilter\fR
|
|
.RS 4
|
|
.sp
|
|
prints the AST (abstract syntax tree) for the expression, which gives full transparency on the precedence and associativity rules of Miller\(cqs grammar\&. Please use a dollar sign for field names and double\-quotes for string literals\&. Miller built\-in variables are NF, NR, FNR, FILENUM, FILENAME, PI, E\&.
|
|
.sp
|
|
Examples:
|
|
.sp
|
|
.if n \{\
|
|
.RS 4
|
|
.\}
|
|
.nf
|
|
mlr filter \*(Aqlog10($count) > 4\&.0\*(Aq
|
|
mlr filter \*(AqFNR == 2 (second record in each file)\*(Aq
|
|
mlr filter \*(Aqurand() < 0\&.001\*(Aq (subsampling)
|
|
mlr filter \*(Aq$color != "blue" && $value > 4\&.2\*(Aq
|
|
mlr filter \*(Aq($x<\&.5 && $y<\&.5) || ($x>\&.5 && $y>\&.5)\*(Aq
|
|
.fi
|
|
.if n \{\
|
|
.RE
|
|
.\}
|
|
.sp
|
|
Please see http://johnkerl\&.org/miller/doc/reference\&.html for more information including function list\&.
|
|
.RE
|
|
.sp
|
|
.it 1 an-trap
|
|
.nr an-no-space-flag 1
|
|
.nr an-break-flag 1
|
|
.br
|
|
.ps +1
|
|
\fBgroup-by\fR
|
|
.RS 4
|
|
.sp
|
|
Usage: mlr group\-by {comma\-separated field names}
|
|
.sp
|
|
Outputs records in batches having identical values at specified field names\&.
|
|
.RE
|
|
.sp
|
|
.it 1 an-trap
|
|
.nr an-no-space-flag 1
|
|
.nr an-break-flag 1
|
|
.br
|
|
.ps +1
|
|
\fBgroup-like\fR
|
|
.RS 4
|
|
.sp
|
|
Usage: mlr group\-like
|
|
.sp
|
|
Outputs records in batches having identical field names\&.
|
|
.RE
|
|
.sp
|
|
.it 1 an-trap
|
|
.nr an-no-space-flag 1
|
|
.nr an-break-flag 1
|
|
.br
|
|
.ps +1
|
|
\fBhaving-fields\fR
|
|
.RS 4
|
|
.sp
|
|
Usage: mlr having\-fields [options]
|
|
.sp
|
|
Conditionally passes through records depending on each record\(cqs field names\&.
|
|
.sp
|
|
Options:
|
|
.sp
|
|
\-\-at\-least {a,b,c} \-\-which\-are {a,b,c} \-\-at\-most {a,b,c}
|
|
.RE
|
|
.sp
|
|
.it 1 an-trap
|
|
.nr an-no-space-flag 1
|
|
.nr an-break-flag 1
|
|
.br
|
|
.ps +1
|
|
\fBhead\fR
|
|
.RS 4
|
|
.sp
|
|
Usage: mlr head [options]
|
|
.sp
|
|
Passes through the first n records, optionally by category\&.
|
|
.sp
|
|
Options:
|
|
.PP
|
|
.RS 4
|
|
Head count to print; default 10
|
|
.RE
|
|
.PP
|
|
\-g {a,b,c}
|
|
.RS 4
|
|
Optional group\-by\-field names for head counts
|
|
.RE
|
|
.RE
|
|
.sp
|
|
.it 1 an-trap
|
|
.nr an-no-space-flag 1
|
|
.nr an-break-flag 1
|
|
.br
|
|
.ps +1
|
|
\fBhistogram\fR
|
|
.RS 4
|
|
.sp
|
|
Usage: mlr histogram [options]
|
|
.sp
|
|
Just a histogram\&. Input values < lo or > hi are not counted\&.
|
|
.sp
|
|
Options:
|
|
.PP
|
|
\-f {a,b,c}
|
|
.RS 4
|
|
Value\-field names for histogram counts
|
|
.RE
|
|
.PP
|
|
.RS 4
|
|
Histogram low value
|
|
.RE
|
|
.PP
|
|
.RS 4
|
|
Histogram high value
|
|
.RE
|
|
.PP
|
|
.RS 4
|
|
Number of histogram bins
|
|
.RE
|
|
.RE
|
|
.sp
|
|
.it 1 an-trap
|
|
.nr an-no-space-flag 1
|
|
.nr an-break-flag 1
|
|
.br
|
|
.ps +1
|
|
\fBjoin\fR
|
|
.RS 4
|
|
.sp
|
|
Usage: mlr join [options]
|
|
.sp
|
|
Joins records from specified left file name with records from all file names at the end of the Miller argument list\&. Functionality is essentially the same as the system "join" command, but for record streams\&.
|
|
.sp
|
|
Options:
|
|
.sp
|
|
.if n \{\
|
|
.RS 4
|
|
.\}
|
|
.nf
|
|
\-f {left file name}
|
|
\-j {a,b,c} Comma\-separated join\-field names for output
|
|
\-l {a,b,c} Comma\-separated join\-field names for left input file; defaults to \-j values if omitted\&.
|
|
\-r {a,b,c} Comma\-separated join\-field names for right input file(s); defaults to \-j values if omitted\&.
|
|
\-\-lp {text} Additional prefix for non\-join output field names from the left file
|
|
\-\-rp {text} Additional prefix for non\-join output field names from the right file(s)
|
|
\-\-np Do not emit paired records
|
|
\-\-ul Emit unpaired records from the left file
|
|
\-\-ur Emit unpaired records from the right file(s)
|
|
\-u Enable unsorted input\&. In this case, the entire left file will be loaded into memory\&.
|
|
Without \-u, records must be sorted lexically by their join\-field names, else not all
|
|
records will be paired\&.
|
|
.fi
|
|
.if n \{\
|
|
.RE
|
|
.\}
|
|
.sp
|
|
File\-format options default to those for the right file names on the Miller argument list, but may be overridden for the left file as follows\&. Please see the main "mlr \-\-help" for more information on syntax for these arguments\&.
|
|
.sp
|
|
.if n \{\
|
|
.RS 4
|
|
.\}
|
|
.nf
|
|
\-i {one of csv,dkvp,nidx,pprint,xtab}
|
|
\-\-irs {record\-separator character}
|
|
\-\-ifs {field\-separator character}
|
|
\-\-ips {pair\-separator character}
|
|
\-\-repifs
|
|
\-\-repips
|
|
\-\-use\-mmap
|
|
\-\-no\-mmap
|
|
.fi
|
|
.if n \{\
|
|
.RE
|
|
.\}
|
|
.sp
|
|
Please see http://johnkerl\&.org/miller/doc/reference\&.html for more information including examples\&.
|
|
.RE
|
|
.sp
|
|
.it 1 an-trap
|
|
.nr an-no-space-flag 1
|
|
.nr an-break-flag 1
|
|
.br
|
|
.ps +1
|
|
\fBlabel\fR
|
|
.RS 4
|
|
.sp
|
|
Usage: mlr label {new1,new2,new3,\&...}
|
|
.sp
|
|
Given n comma\-separated names, renames the first n fields of each record to have the respective name\&. (Fields past the nth are left with their original names\&.) Particularly useful with \-\-inidx, to give useful names to otherwise integer\-indexed fields\&.
|
|
.RE
|
|
.sp
|
|
.it 1 an-trap
|
|
.nr an-no-space-flag 1
|
|
.nr an-break-flag 1
|
|
.br
|
|
.ps +1
|
|
\fBput\fR
|
|
.RS 4
|
|
.sp
|
|
Adds/updates specified field(s)\&.
|
|
.sp
|
|
With \-v, first prints the AST (abstract syntax tree) for the expression, which gives full transparency on the precedence and associativity rules of Miller\(cqs grammar\&. Please use a dollar sign for field names and double\-quotes for string literals\&. Miller built\-in variables are NF, NR, FNR, FILENUM, FILENAME, PI, E\&. Multiple assignments may be separated with a semicolon\&.
|
|
.sp
|
|
Examples:
|
|
.sp
|
|
.if n \{\
|
|
.RS 4
|
|
.\}
|
|
.nf
|
|
mlr put \*(Aq$y = log10($x); $z = sqrt($y)\*(Aq
|
|
mlr put \*(Aq$filename = FILENAME\*(Aq
|
|
mlr put \*(Aq$colored_shape = $color \&. "_" \&. $shape\*(Aq
|
|
mlr put \*(Aq$y = cos($theta); $z = atan2($y, $x)\*(Aq
|
|
.fi
|
|
.if n \{\
|
|
.RE
|
|
.\}
|
|
.sp
|
|
Please see http://johnkerl\&.org/miller/doc/reference\&.html for more information including function list\&.
|
|
.RE
|
|
.sp
|
|
.it 1 an-trap
|
|
.nr an-no-space-flag 1
|
|
.nr an-break-flag 1
|
|
.br
|
|
.ps +1
|
|
\fBregularize\fR
|
|
.RS 4
|
|
.sp
|
|
Usage: mlr regularize
|
|
.sp
|
|
For records seen earlier in the data stream with same field names in a different order, outputs them with field names in the previously encountered order\&.
|
|
.sp
|
|
Example:
|
|
.sp
|
|
input records a=1,c=2,b=3, then e=4,d=5, then c=7,a=6,b=8 output as a=1,c=2,b=3, then e=4,d=5, then a=6,c=7,b=8
|
|
.RE
|
|
.sp
|
|
.it 1 an-trap
|
|
.nr an-no-space-flag 1
|
|
.nr an-break-flag 1
|
|
.br
|
|
.ps +1
|
|
\fBrename\fR
|
|
.RS 4
|
|
.sp
|
|
Usage: mlr rename {old1,new1,old2,new2,\&...}
|
|
.sp
|
|
Renames specified fields\&.
|
|
.RE
|
|
.sp
|
|
.it 1 an-trap
|
|
.nr an-no-space-flag 1
|
|
.nr an-break-flag 1
|
|
.br
|
|
.ps +1
|
|
\fBreorder\fR
|
|
.RS 4
|
|
.sp
|
|
Usage: mlr reorder [options]
|
|
.sp
|
|
Options:
|
|
.PP
|
|
\-f {a,b,c}
|
|
.RS 4
|
|
Field names to reorder\&.
|
|
.RE
|
|
.PP
|
|
\-e
|
|
.RS 4
|
|
Put specified field names at record end: default is to put at record start\&.
|
|
.RE
|
|
.sp
|
|
Examples:
|
|
.sp
|
|
.if n \{\
|
|
.RS 4
|
|
.\}
|
|
.nf
|
|
mlr reorder \-f a,b sends input record "d=4,b=2,a=1,c=3" to "a=1,b=2,d=4,c=3"\&.
|
|
mlr reorder \-e \-f a,b sends input record "d=4,b=2,a=1,c=3" to "d=4,c=3,a=1,b=2"\&.
|
|
.fi
|
|
.if n \{\
|
|
.RE
|
|
.\}
|
|
.RE
|
|
.sp
|
|
.it 1 an-trap
|
|
.nr an-no-space-flag 1
|
|
.nr an-break-flag 1
|
|
.br
|
|
.ps +1
|
|
\fBsort\fR
|
|
.RS 4
|
|
.sp
|
|
Sorts records primarily by the first specified field, secondarily by the second field, and so on\&.
|
|
.sp
|
|
Flags:
|
|
.PP
|
|
\-f {comma\-separated field names}
|
|
.RS 4
|
|
Lexical ascending
|
|
.RE
|
|
.PP
|
|
\-n {comma\-separated field names}
|
|
.RS 4
|
|
Numerical ascending; nulls sort last
|
|
.RE
|
|
.PP
|
|
\-nf {comma\-separated field names}
|
|
.RS 4
|
|
Numerical ascending; nulls sort last
|
|
.RE
|
|
.PP
|
|
\-r {comma\-separated field names}
|
|
.RS 4
|
|
Lexical descending
|
|
.RE
|
|
.PP
|
|
\-nr {comma\-separated field names}
|
|
.RS 4
|
|
Numerical descending; nulls sort first
|
|
.RE
|
|
.sp
|
|
Example:
|
|
.sp
|
|
.if n \{\
|
|
.RS 4
|
|
.\}
|
|
.nf
|
|
mlr sort \-f a,b \-nr x,y,z
|
|
.fi
|
|
.if n \{\
|
|
.RE
|
|
.\}
|
|
.sp
|
|
which is the same as:
|
|
.sp
|
|
.if n \{\
|
|
.RS 4
|
|
.\}
|
|
.nf
|
|
mlr sort \-f a \-f b \-nr x \-nr y \-nr z
|
|
.fi
|
|
.if n \{\
|
|
.RE
|
|
.\}
|
|
.RE
|
|
.sp
|
|
.it 1 an-trap
|
|
.nr an-no-space-flag 1
|
|
.nr an-break-flag 1
|
|
.br
|
|
.ps +1
|
|
\fBstats1\fR
|
|
.RS 4
|
|
.sp
|
|
Usage: mlr stats1 [options]
|
|
.PP
|
|
\-a {sum,count,\&...}
|
|
.RS 4
|
|
Names of accumulators:
|
|
p10,
|
|
p25\&.2,
|
|
p50,
|
|
p98,
|
|
p100, etc\&. and/or one or more of:
|
|
count,
|
|
mode,
|
|
sum,
|
|
mean,
|
|
stddev,
|
|
var,
|
|
meaneb,
|
|
min,
|
|
max\&.
|
|
.RE
|
|
.PP
|
|
\-f {a,b,c}
|
|
.RS 4
|
|
Value\-field names on which to compute statistics
|
|
.RE
|
|
.PP
|
|
\-g {d,e,f}
|
|
.RS 4
|
|
Optional group\-by\-field names
|
|
.RE
|
|
.sp
|
|
Examples:
|
|
.sp
|
|
.if n \{\
|
|
.RS 4
|
|
.\}
|
|
.nf
|
|
mlr stats1 \-a min,p10,p50,p90,max \-f value \-g size,shape
|
|
mlr stats1 \-a count,mode \-f size
|
|
mlr stats1 \-a count,mode \-f size \-g shape
|
|
.fi
|
|
.if n \{\
|
|
.RE
|
|
.\}
|
|
.sp
|
|
Notes:
|
|
.sp
|
|
.RS 4
|
|
.ie n \{\
|
|
\h'-04'\(bu\h'+03'\c
|
|
.\}
|
|
.el \{\
|
|
.sp -1
|
|
.IP \(bu 2.3
|
|
.\}
|
|
p50 is a synonym for median\&.
|
|
.RE
|
|
.sp
|
|
.RS 4
|
|
.ie n \{\
|
|
\h'-04'\(bu\h'+03'\c
|
|
.\}
|
|
.el \{\
|
|
.sp -1
|
|
.IP \(bu 2.3
|
|
.\}
|
|
min and max output the same results as p0 and p100, respectively, but use less memory\&.
|
|
.RE
|
|
.sp
|
|
.RS 4
|
|
.ie n \{\
|
|
\h'-04'\(bu\h'+03'\c
|
|
.\}
|
|
.el \{\
|
|
.sp -1
|
|
.IP \(bu 2.3
|
|
.\}
|
|
count and mode allow text input; the rest require numeric input\&. In particular, 1 and 1\&.0 are distinct text for count and mode\&.
|
|
.RE
|
|
.sp
|
|
.RS 4
|
|
.ie n \{\
|
|
\h'-04'\(bu\h'+03'\c
|
|
.\}
|
|
.el \{\
|
|
.sp -1
|
|
.IP \(bu 2.3
|
|
.\}
|
|
When there are mode ties, the first\-encountered datum wins\&.
|
|
.RE
|
|
.RE
|
|
.sp
|
|
.it 1 an-trap
|
|
.nr an-no-space-flag 1
|
|
.nr an-break-flag 1
|
|
.br
|
|
.ps +1
|
|
\fBstats2\fR
|
|
.RS 4
|
|
.sp
|
|
Usage: mlr stats2 [options]
|
|
.PP
|
|
\-a {linreg\-ols,corr,\&...}
|
|
.RS 4
|
|
Names of accumulators: one or more of
|
|
linreg\-pca,
|
|
linreg\-ols,
|
|
r2,
|
|
corr,
|
|
cov,
|
|
covx\&.
|
|
r2
|
|
is a quality metric for
|
|
linreg\-ols;
|
|
linrec\-pca
|
|
outputs its own quality metric\&.
|
|
.RE
|
|
.PP
|
|
\-f {a,b,c,d}
|
|
.RS 4
|
|
Value\-field name\-pairs on which to compute statistics\&. There must be an even number of names\&.
|
|
.RE
|
|
.PP
|
|
\-g {e,f,g}
|
|
.RS 4
|
|
Optional group\-by\-field names\&.
|
|
.RE
|
|
.PP
|
|
\-v
|
|
.RS 4
|
|
Print additional output for
|
|
linreg\-pca\&.
|
|
.RE
|
|
.sp
|
|
Examples:
|
|
.sp
|
|
.if n \{\
|
|
.RS 4
|
|
.\}
|
|
.nf
|
|
mlr stats2 \-a linreg\-pca \-f x,y
|
|
mlr stats2 \-a linreg\-ols,r2 \-f x,y \-g size,shape
|
|
mlr stats2 \-a corr \-f x,y
|
|
.fi
|
|
.if n \{\
|
|
.RE
|
|
.\}
|
|
.RE
|
|
.sp
|
|
.it 1 an-trap
|
|
.nr an-no-space-flag 1
|
|
.nr an-break-flag 1
|
|
.br
|
|
.ps +1
|
|
\fBstep\fR
|
|
.RS 4
|
|
.sp
|
|
Usage: mlr step [options]
|
|
.sp
|
|
Computes values dependent on the previous record, optionally grouped by category\&.
|
|
.PP
|
|
\-a {delta,rsum,\&...}
|
|
.RS 4
|
|
Names of steppers: one or more of delta rsum counter
|
|
.RE
|
|
.PP
|
|
\-f {a,b,c}
|
|
.RS 4
|
|
Value\-field names on which to compute statistics
|
|
.RE
|
|
.PP
|
|
\-g {d,e,f}
|
|
.RS 4
|
|
Group\-by\-field names
|
|
.RE
|
|
.RE
|
|
.sp
|
|
.it 1 an-trap
|
|
.nr an-no-space-flag 1
|
|
.nr an-break-flag 1
|
|
.br
|
|
.ps +1
|
|
\fBtac\fR
|
|
.RS 4
|
|
.sp
|
|
Usage: mlr tac
|
|
.sp
|
|
Prints records in reverse order from the order in which they were encountered\&.
|
|
.RE
|
|
.sp
|
|
.it 1 an-trap
|
|
.nr an-no-space-flag 1
|
|
.nr an-break-flag 1
|
|
.br
|
|
.ps +1
|
|
\fBtail\fR
|
|
.RS 4
|
|
.sp
|
|
Usage: mlr tail [options]
|
|
.sp
|
|
Passes through the last n records, optionally by category\&.
|
|
.PP
|
|
.RS 4
|
|
Tail count to print; default 10
|
|
.RE
|
|
.PP
|
|
\-g {a,b,c}
|
|
.RS 4
|
|
Optional group\-by\-field names for tail counts
|
|
.RE
|
|
.RE
|
|
.sp
|
|
.it 1 an-trap
|
|
.nr an-no-space-flag 1
|
|
.nr an-break-flag 1
|
|
.br
|
|
.ps +1
|
|
\fBtop\fR
|
|
.RS 4
|
|
.sp
|
|
Usage: mlr top [options]
|
|
.sp
|
|
Prints the n records with smallest/largest values at specified fields, optionally by category\&.
|
|
.PP
|
|
\-f {a,b,c}
|
|
.RS 4
|
|
Value\-field names for top counts
|
|
.RE
|
|
.PP
|
|
\-g {d,e,f}
|
|
.RS 4
|
|
Optional group\-by\-field names for top counts
|
|
.RE
|
|
.PP
|
|
.RS 4
|
|
How many records to print per category; default 1
|
|
.RE
|
|
.PP
|
|
\-a
|
|
.RS 4
|
|
Print all fields for top\-value records; default is to print only value and group\-by fields\&.
|
|
.RE
|
|
.PP
|
|
\-\-min
|
|
.RS 4
|
|
Print top smallest values; default is top largest values
|
|
.RE
|
|
.RE
|
|
.sp
|
|
.it 1 an-trap
|
|
.nr an-no-space-flag 1
|
|
.nr an-break-flag 1
|
|
.br
|
|
.ps +1
|
|
\fBuniq\fR
|
|
.RS 4
|
|
.sp
|
|
Usage: mlr uniq [options]
|
|
.sp
|
|
Prints distinct values for specified field names\&. With \-c, same as count\-distinct\&.
|
|
.PP
|
|
\-g {d,e,f}
|
|
.RS 4
|
|
Group\-by\-field names for uniq counts
|
|
.RE
|
|
.PP
|
|
\-c
|
|
.RS 4
|
|
Show repeat counts in addition to unique values
|
|
.RE
|
|
.RE
|
|
.SH "AUTHOR"
|
|
.sp
|
|
miller is written by John Kerl <kerl\&.john\&.r@gmail\&.com>\&.
|
|
.sp
|
|
This manual page has been composed from miller\(cqs help output by Eric MSP Veith <eveith@veith\-m\&.de>\&.
|
|
.SH "SEE ALSO"
|
|
.sp
|
|
sed(1), awk(1), cut(1), join(1), sort(1), RFC 4180: Common Format and MIME Type for Comma\-Separated Values (CSV) Files, the miller website http://johnkerl\&.org/miller/doc
|